Merge tag 'v4.3-rc3' into x86/urgent, before applying dependent fix

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 57 insertions, 37 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5a5d79ee256f..d5eb4ad1c534 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
+#include <linux/memcontrol.h>
 #include <linux/blk-cgroup.h>
 #include <linux/backing-dev-defs.h>
 #include <linux/slab.h>
@@ -252,13 +253,19 @@ int inode_congested(struct inode *inode, int cong_bits);
  * @inode: inode of interest
  *
  * cgroup writeback requires support from both the bdi and filesystem.
- * Test whether @inode has both.
+ * Also, both memcg and iocg have to be on the default hierarchy.  Test
+ * whether all conditions are met.
+ *
+ * Note that the test result may change dynamically on the same inode
+ * depending on how memcg and iocg are configured.
  */
 static inline bool inode_cgwb_enabled(struct inode *inode)
 {
         struct backing_dev_info *bdi = inode_to_bdi(inode);
 
-        return bdi_cap_account_dirty(bdi) &&
+        return cgroup_on_dfl(mem_cgroup_root_css->cgroup) &&
+                cgroup_on_dfl(blkcg_root_css->cgroup) &&
+                bdi_cap_account_dirty(bdi) &&
                 (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
                 (inode->i_sb->s_iflags & SB_I_CGROUPWB);
 }
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4d8fcf2187dc..8492721b39be 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -473,31 +473,8 @@ struct cgroup_subsys {
         unsigned int depends_on;
 };
 
-extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
-
-/**
- * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_begin() and allows cgroup operations to
- * synchronize against threadgroup changes using a percpu_rw_semaphore.
- */
-static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
-{
-        percpu_down_read(&cgroup_threadgroup_rwsem);
-}
-
-/**
- * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_end().  Counterpart of
- * cgroup_threadcgroup_change_begin().
- */
-static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
-{
-        percpu_up_read(&cgroup_threadgroup_rwsem);
-}
+void cgroup_threadgroup_change_begin(struct task_struct *tsk);
+void cgroup_threadgroup_change_end(struct task_struct *tsk);
 
 #else   /* CONFIG_CGROUPS */
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index d0b380ee7d67..e38681f4912d 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -25,6 +25,13 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
+#ifdef CONFIG_CGROUPS
+#define INIT_GROUP_RWSEM(sig)                                           \
+        .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem),
+#else
+#define INIT_GROUP_RWSEM(sig)
+#endif
+
 #ifdef CONFIG_CPUSETS
 #define INIT_CPUSET_SEQ(tsk)                                                    \
         .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq),
@@ -57,6 +64,7 @@ extern struct fs_struct init_fs;
         INIT_PREV_CPUTIME(sig)                                          \
         .cred_guard_mutex =                                             \
                  __MUTEX_INITIALIZER(sig.cred_guard_mutex),             \
+        INIT_GROUP_RWSEM(sig)                                           \
 }
 
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88a00694eda5..2d15e3831440 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n)
         BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
         smp_mb__before_atomic();
         clear_bit(NAPI_STATE_SCHED, &n->state);
+        clear_bit(NAPI_STATE_NPSVC, &n->state);
 }
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 962387a192f1..4a4e3a092337 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -19,6 +19,7 @@
 #include <linux/spinlock.h>
 #include <linux/ethtool.h>
 #include <linux/mii.h>
+#include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/mod_devicetable.h>
@@ -153,6 +154,7 @@ struct sk_buff;
  * PHYs should register using this structure
  */
 struct mii_bus {
+        struct module *owner;
         const char *name;
         char id[MII_BUS_ID_SIZE];
         void *priv;
@@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void)
         return mdiobus_alloc_size(0);
 }
 
-int mdiobus_register(struct mii_bus *bus);
+int __mdiobus_register(struct mii_bus *bus, struct module *owner);
+#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE)
 void mdiobus_unregister(struct mii_bus *bus);
 void mdiobus_free(struct mii_bus *bus);
 struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv);
@@ -742,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
                                      struct phy_c45_device_ids *c45_ids);
 struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45);
 int phy_device_register(struct phy_device *phy);
+void phy_device_remove(struct phy_device *phydev);
 int phy_init_hw(struct phy_device *phydev);
 int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a4ab9daa387c..b7b9501b41af 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -762,6 +762,18 @@ struct signal_struct {
         unsigned audit_tty_log_passwd;
         struct tty_audit_buf *tty_audit_buf;
 #endif
+#ifdef CONFIG_CGROUPS
+        /*
+         * group_rwsem prevents new tasks from entering the threadgroup and
+         * member tasks from exiting,a more specifically, setting of
+         * PF_EXITING.  fork and exit paths are protected with this rwsem
+         * using threadgroup_change_begin/end().  Users which require
+         * threadgroup to remain stable should use threadgroup_[un]lock()
+         * which also takes care of exec path.  Currently, cgroup is the
+         * only user.
+         */
+        struct rw_semaphore group_rwsem;
+#endif
 
         oom_flags_t oom_flags;
         short oom_score_adj;            /* OOM kill score adjustment */
diff --git a/include/linux/security.h b/include/linux/security.h
index 79d85ddf8093..2f4c1f7aa7db 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -946,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2,
                                       unsigned long arg4,
                                       unsigned long arg5)
 {
-        return cap_task_prctl(option, arg2, arg3, arg3, arg5);
+        return cap_task_prctl(option, arg2, arg3, arg4, arg5);
 }
 
 static inline void security_task_to_inode(struct task_struct *p, struct inode *inode)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2738d355cdf9..2b0a30a6e31c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -179,6 +179,9 @@ struct nf_bridge_info {
         u8                      bridged_dnat:1;
         __u16                   frag_max_size;
         struct net_device       *physindev;
+
+        /* always valid & non-NULL from FORWARD on, for physdev match */
+        struct net_device       *physoutdev;
         union {
                 /* prerouting: detect dnat in orig/reply direction */
                 __be32          ipv4_daddr;
@@ -189,9 +192,6 @@ struct nf_bridge_info {
                  * skb is out in neigh layer.
                  */
                 char neigh_header[8];
-
-                /* always valid & non-NULL from FORWARD on, for physdev match */
-                struct net_device *physoutdev;
         };
 };
 #endif
@@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 {
         if (skb->ip_summed == CHECKSUM_COMPLETE)
                 skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
+        else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+                 skb_checksum_start_offset(skb) <= len)
+                skb->ip_summed = CHECKSUM_NONE;
 }
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 269e8afd3e2a..6b00f18f5e6b 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -34,7 +34,7 @@ extern struct bus_type spi_bus_type;
 
 /**
  * struct spi_statistics - statistics for spi transfers
- * @clock:         lock protecting this structure
+ * @lock:          lock protecting this structure
  *
  * @messages:      number of spi-messages handled
  * @transfers:     number of spi_transfers handled
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 7591788e9fbf..357e44c1a46b 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -42,6 +42,7 @@ struct sock_xprt {
         /*
          * Connection of transports
          */
+        unsigned long           sock_state;
         struct delayed_work     connect_worker;
         struct sockaddr_storage srcaddr;
         unsigned short          srcport;
@@ -76,6 +77,8 @@ struct sock_xprt {
  */
 #define TCP_RPC_REPLY           (1UL << 6)
 
+#define XPRT_SOCK_CONNECTING    1U
+
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_SUNRPC_XPRTSOCK_H */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 17292fee8686..157d366e761b 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -360,7 +360,7 @@ static inline struct thermal_zone_device *
 thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
                                 const struct thermal_zone_of_device_ops *ops)
 {
-        return NULL;
+        return ERR_PTR(-ENODEV);
 }
 
 static inline
@@ -380,6 +380,8 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
 
 int power_actor_get_max_power(struct thermal_cooling_device *,
                               struct thermal_zone_device *tz, u32 *max_power);
+int power_actor_get_min_power(struct thermal_cooling_device *,
+                              struct thermal_zone_device *tz, u32 *min_power);
 int power_actor_set_power(struct thermal_cooling_device *,
                           struct thermal_instance *, u32);
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
@@ -415,6 +417,10 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
 static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev,
                               struct thermal_zone_device *tz, u32 *max_power)
 { return 0; }
+static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev,
+                                            struct thermal_zone_device *tz,
+                                            u32 *min_power)
+{ return -ENODEV; }
 static inline int power_actor_set_power(struct thermal_cooling_device *cdev,
                           struct thermal_instance *tz, u32 power)
 { return 0; }
diff --git a/include/linux/wait.h b/include/linux/wait.h
index d3d077228d4c..1e1bf9f963a9 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 
 typedef int wait_bit_action_f(struct wait_bit_key *);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
-                          void *key);
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up_poll(x, m)                                              \
         __wake_up(x, TASK_NORMAL, 1, (void *) (m))
 #define wake_up_locked_poll(x, m)                                       \
-        __wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m))
+        __wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
 #define wake_up_interruptible_poll(x, m)                                \
         __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
 #define wake_up_interruptible_sync_poll(x, m)                           \